CN107507377A - The signal processing method and device of optical fiber perimeter system - Google Patents
The signal processing method and device of optical fiber perimeter system Download PDFInfo
- Publication number
- CN107507377A CN107507377A CN201710669830.7A CN201710669830A CN107507377A CN 107507377 A CN107507377 A CN 107507377A CN 201710669830 A CN201710669830 A CN 201710669830A CN 107507377 A CN107507377 A CN 107507377A
- Authority
- CN
- China
- Prior art keywords
- chromosome
- population
- fitness
- mrow
- signal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/02—Mechanical actuation
- G08B13/12—Mechanical actuation by the breaking or disturbance of stretched cords or wires
- G08B13/122—Mechanical actuation by the breaking or disturbance of stretched cords or wires for a perimeter fence
- G08B13/124—Mechanical actuation by the breaking or disturbance of stretched cords or wires for a perimeter fence with the breaking or disturbance being optically detected, e.g. optical fibers in the perimeter fence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Theoretical Computer Science (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Genetics & Genomics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Physiology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a kind of signal processing method and device of optical fiber perimeter system.Methods described includes：Characteristic signal fragment of the extraction with setting signal feature from time domain fiber-optic signal；The characteristic signal fragment is encoded, obtains corresponding chromosome, to complete the initialization of population；Fitness calculating is carried out to the chromosome in the population using artificial neural network；According to the fitness being calculated, genetic manipulation is carried out to the chromosome in the population；Above-mentioned fitness calculating and genetic manipulation are repeated, until obtaining the optimal solution of the population；According to the chromosome in the optimal solution, the type of Means of Intrusion is identified.The signal processing method and device of optical fiber perimeter system provided in an embodiment of the present invention improve the accuracy rate and speed of intrusion behavior identification.
Description
Technical field
The present embodiments relate to safety monitoring technology field, more particularly to a kind of signal transacting side of optical fiber perimeter system
Method and device.
Background technology
In recent years, the science technicalization with illegal invasion means and complication, safety precaution have turned into national economy and sent out
A vital task in exhibition.At present, traditional security device such as fence, enclosure wall, iron wire and hedge net and technology are difficult to adapt to want
Evil department and the needs of key unit's safeguarding work, and the simple manpower precautionary measures are limited to time, region and personnel
The factors such as energy, start a leak and slip up again and again.
Under the trend of light entering and copper back, to industry-by-industry, it is applicable not only to communications and appointed extensive utilization optical fiber
Business, and can also be used as the sensor of security monitoring.When external interferences such as optical fiber under tension, displacement, vibration and temperature
When, the feature of optical signal will change, and can quantify external interference using special sensor device, monitor around optical fiber
Environmental change.Further, since optical fiber is a kind of passive device in itself, field is used without powering, and electromagnetism interference and is easy to
The advantage of laying makes it progressively turn into the major product in circumference security protection.
In traditional optical fiber perimeter system, utilize artificial neural network (Artificial neural network, ANN)
To identify intrusion behavior.Due to the light perimeter system of the complexity of ANN in itself, in this way progress intrusion behavior identification
In the prevalence of the disadvantage that recognition accuracy is relatively low, recognition speed is partially slow.
The content of the invention
For above-mentioned technical problem, the embodiments of the invention provide a kind of signal processing method and dress of optical fiber perimeter system
Put, to improve the accuracy rate and speed of intrusion behavior identification.
On the one hand, the embodiments of the invention provide a kind of signal processing method of optical fiber perimeter system, methods described to include：
Characteristic signal fragment of the extraction with setting signal feature from time domain fiber-optic signal；
The characteristic signal fragment is encoded, obtains corresponding chromosome, to complete the initialization of population；
Fitness calculating is carried out to the chromosome in the population using artificial neural network；
According to the fitness being calculated, genetic manipulation is carried out to the chromosome in the population；
Above-mentioned fitness calculating and genetic manipulation are repeated, until obtaining the optimal solution of the population；
According to the chromosome in the optimal solution, the type of Means of Intrusion is identified.
On the other hand, the embodiment of the present invention additionally provides a kind of signal processing apparatus of optical fiber perimeter system, described device
Including：
Extraction module, for characteristic signal fragment of the extraction with setting signal feature from time domain fiber-optic signal；
Coding module, for being encoded to the characteristic signal fragment, corresponding chromosome is obtained, to complete population
Initialization；
Computing module, for carrying out fitness calculating to the chromosome in the population using artificial neural network；
Hereditary module, for according to the fitness being calculated, genetic manipulation to be carried out to the chromosome in the population；
Module is repeated, for repeating above-mentioned fitness calculating and genetic manipulation, until obtaining the optimal of the population
Solution；
Identification module, for the chromosome in the optimal solution, identify the type of Means of Intrusion.
The signal processing method and device of optical fiber perimeter system provided in an embodiment of the present invention, pass through genetic algorithm and ANN
The mode being combined carries out the identification of Means of Intrusion, not only increases the accuracy rate of intrusion behavior identification, and improves invasion
The speed of Activity recognition.
Brief description of the drawings
By reading the detailed description made to non-limiting example made with reference to the following drawings, of the invention is other
Feature, objects and advantages will become more apparent upon：
Fig. 1 is the flow chart figure of the signal processing method for the optical fiber perimeter system that first embodiment of the invention provides；
Fig. 2 is the flow that operation is identified in the signal processing method for the optical fiber perimeter system that second embodiment of the invention provides
Figure；
Fig. 3 is the structure chart of the signal processing apparatus for the optical fiber perimeter system that third embodiment of the invention provides.
Embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that in order to just
Part related to the present invention rather than entire infrastructure are illustrate only in description, accompanying drawing.
First embodiment
Present embodiments provide a kind of technical scheme of the signal processing method of optical fiber perimeter system.In the technical scheme
In, the signal processing method of optical fiber perimeter system includes：Feature of the extraction with setting signal feature from time domain fiber-optic signal
Signal segment；The characteristic signal fragment is encoded, obtains corresponding chromosome, to complete the initialization of population；Utilize
Artificial neural network carries out fitness calculating to the chromosome in the population；According to the fitness being calculated, to the kind
Chromosome in group carries out genetic manipulation；Above-mentioned fitness calculating and genetic manipulation are repeated, until obtaining the optimal of the population
Solution；According to the chromosome in the optimal solution, the type of Means of Intrusion is identified.
Referring to Fig. 1, the signal processing method of optical fiber perimeter system includes：
S11, characteristic signal fragment of the extraction with setting signal feature from time domain fiber-optic signal.
So-called time domain fiber-optic signal is the signal of actual transmissions in optical fiber.Under normal circumstances, time domain fiber-optic signal is to original
Primordium band signal is modulated the signal formed afterwards.Because the transmission of time domain fiber-optic signal may be by outside invading behavior
Interference, therefore, it can distinguish current whether there occurs intrusion behavior, and occur by the identification to its wave character
Intrusion behavior be which kind of intrusion behavior.
The method that the present embodiment provides has not together with conventional method, is not using complete large fragment in time domain
Basis of the signal as identification intrusion behavior, but signal segment of the extraction with setting feature in the time-domain signal of big section,
The basis that these signal segments are identified as intrusion behavior.
The signal segment extracted is referred to as characteristic signal fragment.The foundation of extraction characteristic signal fragment is whether they accord with
Close default signal characteristic.Default signal characteristic can be the feature of signal in time, the feature in frequency, in signal
Any several combination in feature in amplitude, or above-mentioned three.For example, the feature of signal in time can be special
Whether interior in predetermined time interval levy signal segment.Whether feature of the signal in frequency can be characteristic signal fragment pre-
In fixed frequency range.Whether feature of the signal in amplitude can be the amplitude of characteristic signal fragment beyond default amplitude
Scope.
S12, the characteristic signal fragment is encoded, obtains corresponding chromosome, to complete the initialization of population.
The purpose encoded to characteristic signal fragment is to obtain binary representation, can represent corresponding feature letter
The chromosome of number fragment.
Typically, above-mentioned cataloged procedure can be the sampling and quantization to characteristic signal fragment.Wherein, quantizing process is general
Using the means of non-uniform quantizing.
S13, fitness calculating is carried out to the chromosome in the population using ANN.
In the present embodiment, ANN is specifically radial base neural net.The network structure of radial base neural net is using existing
Structure.And after being handled by above-mentioned radial base neural net, corresponding fitness is provided by equation below：
Wherein, N is sample total, and x (j) is the recognition result of j-th of sample.More specifically, x (j) specific value
Have given below：
Wherein, y (j) is the real output value of j-th of output unit of radial base neural net, and y ' (j) is radial direction base god
Desired output through j-th of output unit of network.
S14, according to the fitness being calculated, genetic manipulation is carried out to the chromosome in the population.
Specifically, above-mentioned genetic manipulation includes selection operation, crossover operation and mutation operation.Above-mentioned selection operation,
Crossover operation and mutation operation perform according to the step in existing genetic algorithm.In existing genetic algorithm, grasped for above-mentioned selection
Work, the various mutation of crossover operation and mutation operation and improvement also go for the present embodiment.
S15, above-mentioned fitness calculating and genetic manipulation are repeated, until obtaining the optimal solution of the population.
After completing once above-mentioned genetic manipulation, to the above-mentioned fitness of execution of the chromosome iteration in obtained population
Calculate and hereditary.The stop condition of above-mentioned iterative calculation is to have obtained the optimal solution of population.That is, to the dye in population
The execution fitness of colour solid continuation iteration calculates and genetic manipulation, and any change will not occur again for the chromosome in population,
Or the change occurred is extremely small, then it is considered that having been obtained for the optimal solution of population.
S16, according to the chromosome in the optimal solution, identify the type of Means of Intrusion.
, can be according to the chromosome in population optimal solution, to the type of intrusion behavior after having obtained the optimal solution of population
It is identified.
The present embodiment is carried out by carrying out snippet extraction to the time-domain signal transmitted in optical fiber to the signal segment extracted
Coding, obtains corresponding chromosome, and the fitness of chromosome is calculated using ANN, and heredity is carried out according to the fitness being calculated
Operation, until obtaining optimal solution, the type of intrusion behavior is finally identified according to the value of optimal solution, improve intrusion behavior identification
Accuracy rate and speed.
Second embodiment
The present embodiment further provides the signal transacting of optical fiber perimeter system based on the above embodiment of the present invention
A kind of technical scheme of operation is identified in method.In the technical scheme, according to the chromosome in the optimal solution, identification invasion
The type of means, including：Chromosome in the optimal solution is decoded；Decoded result and default characteristic signal are carried out
Compare；The type of Means of Intrusion is identified according to comparison result.
Referring to Fig. 2, according to the chromosome in the optimal solution, the type of Means of Intrusion is identified, including：
S21, the chromosome in the optimal solution is decoded.
Above-mentioned decoding is the inverse process of cataloged procedure.By above-mentioned decoding operate, there can be the chromosome of binary representation,
Completely recover its corresponding time-domain signal.
S22, decoded result is compared with default characteristic signal.
For different intrusion behavior types, different characteristic signals is corresponding with.To decode obtained time-domain signal with not
Same characteristic signal is compared, and can finally determine the type of intrusion behavior.
Specifically, above-mentioned signal fusing process can be phase between the time-domain signal that decoding obtains and default characteristic signal
Like the calculating of degree.More specifically, it can calculate the two it according to the two difference between same time point up-sampling value
Between similarity degree.
S23, the type of Means of Intrusion is identified according to comparison result.
Specifically, selection is the most similar to decoded result signal, that is, one characteristic signal of similarity degree highest, will
Its intrusion behavior type is as finally identifying obtained intrusion behavior type.
The present embodiment to the chromosome in the optimal solution by decoding, by decoded result and default characteristic signal
It is compared, and the type of Means of Intrusion is identified according to comparison result, realizes the accurate judgement to Means of Intrusion type.
3rd embodiment
Present embodiments provide a kind of technical scheme of the signal processing apparatus of optical fiber perimeter system.In the technical scheme
In, the signal processing apparatus of optical fiber perimeter system includes：Extraction module 61, coding module 62, computing module 63, hereditary module
64th, module 65, and identification module 66 are repeated.
Extraction module 61 is used for characteristic signal fragment of the extraction with setting signal feature from time domain fiber-optic signal.
Coding module 62 is used to encode the characteristic signal fragment, corresponding chromosome is obtained, to complete population
Initialization.
Computing module 63 is used to carry out fitness calculating to the chromosome in the population using artificial neural network.
Hereditary module 64 is used for according to the fitness being calculated, and genetic manipulation is carried out to the chromosome in the population.
Repeat module 65 to be used to repeat above-mentioned fitness calculating and genetic manipulation, until obtaining the optimal of the population
Solution.
Identification module 66 is used for the chromosome in the optimal solution, identifies the type of Means of Intrusion.
Further, the artificial neural network includes：Radial base neural net.
Further, the radial base neural net calculates the fitness of the chromosome according to equation below：
Wherein, x (j) is the recognition result of j-th of sample, and N is sample total.
Further, the hereditary module is specifically used for：
According to the fitness being calculated, selection operation, crossover operation, Yi Jibian are carried out to the chromosome in the population
ETTHER-OR operation.
Further, the identification module includes：
Decoding unit, for being decoded to the chromosome in the optimal solution；
Comparing unit, for decoded result to be compared with default characteristic signal；
Recognition unit, for identifying the type of Means of Intrusion according to comparison result.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, for those skilled in the art
For, the present invention can have various changes and change.All any modifications made within spirit and principles of the present invention, it is equal
Replace, improve etc., it should be included in the scope of the protection.
Claims (10)
- A kind of 1. signal processing method of optical fiber perimeter system, it is characterised in that including：Characteristic signal fragment of the extraction with setting signal feature from time domain fiber-optic signal；The characteristic signal fragment is encoded, obtains corresponding chromosome, to complete the initialization of population；Fitness calculating is carried out to the chromosome in the population using artificial neural network；According to the fitness being calculated, genetic manipulation is carried out to the chromosome in the population；Above-mentioned fitness calculating and genetic manipulation are repeated, until obtaining the optimal solution of the population；According to the chromosome in the optimal solution, the type of Means of Intrusion is identified.
- 2. according to the method for claim 1, it is characterised in that the artificial neural network includes：Radial base neural net.
- 3. according to the method for claim 2, it is characterised in that the radial base neural net calculates institute according to equation below State the fitness of chromosome：<mrow> <msub> <mi>f</mi> <mi>i</mi> </msub> <mo>=</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>j</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>N</mi> </munderover> <mi>x</mi> <mrow> <mo>(</mo> <mi>j</mi> <mo>)</mo> </mrow> <mo>/</mo> <mi>N</mi> </mrow>Wherein, x (j) is the recognition result of j-th of sample, and N is sample total.
- 4. according to the method for claim 1, it is characterised in that according to the fitness being calculated, in the population Chromosome carries out genetic manipulation, including：According to the fitness being calculated, selection operation, crossover operation, and variation behaviour are carried out to the chromosome in the population Make.
- 5. according to the method for claim 1, it is characterised in that according to the chromosome in the optimal solution, identification invasion hand The type of section, including：Chromosome in the optimal solution is decoded；Decoded result is compared with default characteristic signal；The type of Means of Intrusion is identified according to comparison result.
- A kind of 6. signal processing apparatus of optical fiber perimeter system, it is characterised in that including：Extraction module, for characteristic signal fragment of the extraction with setting signal feature from time domain fiber-optic signal；Coding module, for being encoded to the characteristic signal fragment, corresponding chromosome is obtained, to complete the initial of population Change；Computing module, for carrying out fitness calculating to the chromosome in the population using artificial neural network；Hereditary module, for according to the fitness being calculated, genetic manipulation to be carried out to the chromosome in the population；Module is repeated, for repeating above-mentioned fitness calculating and genetic manipulation, until obtaining the optimal solution of the population；Identification module, for the chromosome in the optimal solution, identify the type of Means of Intrusion.
- 7. according to the method for claim 6, it is characterised in that the artificial neural network includes：Radial base neural net.
- 8. according to the method for claim 7, it is characterised in that the radial base neural net calculates institute according to equation below State the fitness of chromosome：<mrow> <msub> <mi>f</mi> <mi>i</mi> </msub> <mo>=</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>j</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>N</mi> </munderover> <mi>x</mi> <mrow> <mo>(</mo> <mi>j</mi> <mo>)</mo> </mrow> <mo>/</mo> <mi>N</mi> </mrow>Wherein, x (j) is the recognition result of j-th of sample, and N is sample total.
- 9. according to the method for claim 6, it is characterised in that the hereditary module is specifically used for：According to the fitness being calculated, selection operation, crossover operation, and variation behaviour are carried out to the chromosome in the population Make.
- 10. according to the method for claim 6, it is characterised in that the identification module includes：Decoding unit, for being decoded to the chromosome in the optimal solution；Comparing unit, for decoded result to be compared with default characteristic signal；Recognition unit, for identifying the type of Means of Intrusion according to comparison result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710669830.7A CN107507377A (en) | 2017-08-08 | 2017-08-08 | The signal processing method and device of optical fiber perimeter system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710669830.7A CN107507377A (en) | 2017-08-08 | 2017-08-08 | The signal processing method and device of optical fiber perimeter system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107507377A true CN107507377A (en) | 2017-12-22 |
Family
ID=60689869
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710669830.7A Pending CN107507377A (en) | 2017-08-08 | 2017-08-08 | The signal processing method and device of optical fiber perimeter system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107507377A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6651046B1 (en) * | 1999-09-17 | 2003-11-18 | Fujitsu Limited | Optimizing apparatus, optimizing method, and storage medium |
| CN102622535A (en) * | 2012-02-27 | 2012-08-01 | 上海电机学院 | Processing method and processing device based on multiple sequence alignment genetic algorithm |
| CN103236127A (en) * | 2013-05-06 | 2013-08-07 | 无锡成电光纤传感科技有限公司 | Fiber fence intrusion monitoring system and pattern recognition method thereof |
| CN103914527A (en) * | 2014-03-28 | 2014-07-09 | 西安电子科技大学 | Graphic image recognition and matching method based on genetic programming algorithms of novel coding modes |
| KR20160149376A (en) * | 2015-06-17 | 2016-12-28 | 아주대학교산학협력단 | User-Independent Activity Recognition Method Using Genetic Algorithm based Feature Selection |
| CN106600869A (en) * | 2016-12-31 | 2017-04-26 | 上海华魏光纤传感技术有限公司 | Fence intrusion identification method for fiber fence security protection system |
| CN106971170A (en) * | 2017-04-07 | 2017-07-21 | 西北工业大学 | A kind of method for carrying out target identification using one-dimensional range profile based on genetic algorithm |
-
2017
- 2017-08-08 CN CN201710669830.7A patent/CN107507377A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6651046B1 (en) * | 1999-09-17 | 2003-11-18 | Fujitsu Limited | Optimizing apparatus, optimizing method, and storage medium |
| CN102622535A (en) * | 2012-02-27 | 2012-08-01 | 上海电机学院 | Processing method and processing device based on multiple sequence alignment genetic algorithm |
| CN103236127A (en) * | 2013-05-06 | 2013-08-07 | 无锡成电光纤传感科技有限公司 | Fiber fence intrusion monitoring system and pattern recognition method thereof |
| CN103914527A (en) * | 2014-03-28 | 2014-07-09 | 西安电子科技大学 | Graphic image recognition and matching method based on genetic programming algorithms of novel coding modes |
| KR20160149376A (en) * | 2015-06-17 | 2016-12-28 | 아주대학교산학협력단 | User-Independent Activity Recognition Method Using Genetic Algorithm based Feature Selection |
| CN106600869A (en) * | 2016-12-31 | 2017-04-26 | 上海华魏光纤传感技术有限公司 | Fence intrusion identification method for fiber fence security protection system |
| CN106971170A (en) * | 2017-04-07 | 2017-07-21 | 西北工业大学 | A kind of method for carrying out target identification using one-dimensional range profile based on genetic algorithm |
Non-Patent Citations (2)
| Title |
|---|
| 张宏宇: "基于遗传算法的入侵检测特征选择", 《信息网络安全》 * |
| 蒋先刚: "《数字图像模式识别工程项目研究》", 31 March 2014 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111649817B (en) | Distributed optical fiber vibration sensor system and mode identification method thereof | |
| CN111901340B (en) | Intrusion detection system and method for energy Internet | |
| CN113488073B (en) | Fake voice detection method and device based on multi-feature fusion | |
| Moti et al. | Discovering future malware variants by generating new malware samples using generative adversarial network | |
| Fang et al. | A novel demodulation system based on continuous wavelet transform | |
| Li et al. | Learning to fool the speaker recognition | |
| Yang et al. | Collaborative RFID intrusion detection with an artificial immune system | |
| Tamura et al. | Novel defense method against audio adversarial example for speech-to-text transcription neural networks | |
| Alrowais et al. | Automated Machine Learning Enabled Cybersecurity Threat Detection in Internet of Things Environment. | |
| CN111241544A (en) | Malicious program identification method and device, electronic equipment and storage medium | |
| CN115828239A (en) | Malicious code detection method based on multi-dimensional data decision fusion | |
| CN111382783A (en) | Malicious software identification method and device and storage medium | |
| CN110969017A (en) | Judicial data processing method and system | |
| CN114640518B (en) | Personalized trigger back door attack method based on audio steganography | |
| Du et al. | Spear or shield: Leveraging generative AI to tackle security threats of intelligent network services | |
| CN105185381A (en) | Intelligent robot-based voice identification system | |
| Ban et al. | Fam: Featuring android malware for deep learning-based familial analysis | |
| US20140111701A1 (en) | Audio Data Spread Spectrum Embedding and Detection | |
| CN107507377A (en) | The signal processing method and device of optical fiber perimeter system | |
| CN111159588B (en) | Malicious URL detection method based on URL imaging technology | |
| CN117272309A (en) | Source code vulnerability detection method and device based on graph neural network and interpretable model | |
| CN115171710B (en) | Speech enhancement method and system for generating countermeasure network based on multi-angle discrimination | |
| Akhtar et al. | Revealing the traces of histogram equalisation in digital images | |
| CN115100592B (en) | Method and device for identifying hidden danger of external damage of power transmission channel and storage medium | |
| Zhou et al. | Mixed event separation and identification based on a convolutional neural network trained with the domain transfer method for a φ-otdr sensing system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171222 |
|
| RJ01 | Rejection of invention patent application after publication |